Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3454 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.1883. Min Range: -4.1883

Max Act: 4.0964. Min Act: -0.0001

Data Index: 212109 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 4.1883. Min Range: -4.1883

Max Act: 4.1883. Min Act: -0.0001

Data Index: 406233 (C4 (Web Text))

Max Activating Token Index: 588

Text #2

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.8949. Min Act: -0.0001

Data Index: 465835 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.6099. Min Act: -0.0001

Data Index: 154794 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.3508. Min Act: -0.0001

Data Index: 1114573 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.6321. Min Act: -0.0001

Data Index: 921193 (C4 (Web Text))

Max Activating Token Index: 140

Text #6

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.3266. Min Act: -0.0001

Data Index: 1240 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.4186. Min Act: -0.0001

Data Index: 976676 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.2205. Min Act: -0.0001

Data Index: 42695 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.3251. Min Act: -0.0001

Data Index: 1229294 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.2490. Min Act: -0.0001

Data Index: 647194 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.3215. Min Act: -0.0001

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.1423. Min Act: -0.0001

Data Index: 1211353 (C4 (Web Text))

Max Activating Token Index: 144

Text #13

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.2558. Min Act: -0.0001

Data Index: 1258432 (C4 (Web Text))

Max Activating Token Index: 320

Text #14

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.2395. Min Act: -0.0001

Data Index: 97719 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 4.1883. Min Range: -4.1883

Max Act: 2.8615. Min Act: -0.0001

Data Index: 1211542 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 4.1883. Min Range: -4.1883

Max Act: 2.7745. Min Act: -0.0001

Data Index: 73384 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 4.1883. Min Range: -4.1883

Max Act: 3.1228. Min Act: -0.0001

Data Index: 565444 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 4.1883. Min Range: -4.1883

Max Act: 2.9555. Min Act: -0.0001

Data Index: 1240557 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 4.1883. Min Range: -4.1883

Max Act: 2.6655. Min Act: -0.0001

Data Index: 1148701 (C4 (Web Text))

Max Activating Token Index: 721